Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal-states of characters in a story. We explicitly model entities, their interactions and the context in which they appear, and learn rich representations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different decisions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis.
Narrative is a ubiquitous component of human communication. Understanding its structure plays a critical role in a wide variety of applications, ranging from simple comparative analyses to enhanced narrative retrieval, comprehension, or reasoning capabilities. Prior research in narratology has highlighted the importance of studying the links between cognitive and linguistic aspects of narratives for effective comprehension. This interdependence is related to the textual semantics and mental language in narratives, referring to characters' motivations, feelings or emotions, and beliefs. However…
Large pre-trained language models (LMs) have demonstrated impressive capabilities in generating long, fluent text; however, there is little to no analysis on their ability to maintain entity coherence and consistency. In this work, we focus on the end task of narrative generation and systematically analyse the long-range entity coherence and consistency in generated stories. First, we propose a set of automatic metrics for measuring model performance in terms of entity usage. Given these metrics, we quantify the limitations of current LMs. Next, we propose augmenting a pre-trained LM with a dy…
Tsinghua University（清华大学）；Guangdong OPPO Mobile Telecommunications Corp., Ltd.（广东OPPO移动通信有限公司）；NetEase Inc.（网易公司）
Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from representing entities as static embeddings of superficial words, while neglecting to model their ever-changing states, i.e., the information they carry, as the text unfolds. Therefore, we extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. We propose a contrastive framework to learn the state re…
Interactive Systems Lab, University of Trento 2 Clinical Psychology；Psychotherapy, University of Ulm
Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease course, etc.). In the Interspeech 2018 ComParE Self-Assessed Affect challenge, the task of valence prediction was framed as a three-class classification problem using 8 seconds fragments from individuals' narratives. As such, the task did not allow for exploring contextual information of the narratives. In this work, we investigate the intrinsic information fro…
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Institute for Artificial Intelligence（人工智能研究院）；School of Psychological and Cognitive Sciences（心理学与认知科学学院）；School of Intelligence Science and Technology（智能科学与技术学院）；State Key Laboratory of General AI（通用人工智能国家重点实验室）；Beijing Key Laboratory of Behavior and Mental Health（北京行为与心理健康重点实验室）；PKU-Changsha Institute for Computing and Digital Economy（北京大学长沙计算与数字经济研究院）
Patterns vs. Patients: Evaluating LLMs against Mental Health Professionals on Personality Disorder Diagnosis through First-Person Narratives
IDEAS Research Institute（IDEAS研究 institute）；Adam Mickiewicz University（亚当·密茨凯维奇大学）；AMU Center for Artificial Intelligence（AMU人工智能中心）；Poznań University of Medical Sciences（波兹南医学科学大学）；Maria Curie-Skłodowska University（玛丽·居里-斯克洛多夫斯卡大学）
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
Intelligent Systems, Afeka Academic College of Engineering（阿法卡学术工程学院智能系统）；School of Computer Science, Faculty of Sciences, Holon Institute of Technology（霍隆理工学院计算机科学学院）
Artificial Intelligence Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）
With strong marketing advocacy of the benefits of cannabis use for improved mental health, cannabis legalization is a priority among legislators. However, preliminary scientific research does not conclusively associate cannabis with improved mental health. In this study, we explore the relationship between depression and consumption of cannabis in a targeted social media corpus involving personal use of cannabis with the intent to derive its potential mental health benefit. We use tweets that contain an association among three categories annotated by domain experts - Reason, Effect, and Addict…
A Counterfactual Graph Approach to Oppositional Narrative Analysis
Faculty of Engineering, University of Deusto, Bilbao, Spain（德乌斯托大学工程学院，比斯开，西班牙）；Deusto Institute of Technology, University of Deusto, Bilbao, Spain（德乌斯托技术研究所，德乌斯托大学，比斯开，西班牙）
InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
Department of Mathematics, IIT Delhi（印度德里理工学院数学系）；Department of Electrical Engineering, IIT Delhi（印度德里理工学院电气工程系）；Department of Computer Science and Engineering, IIIT Manipur（曼尼普尔理工学院计算机科学与工程系）
This paper describes the second-placed system on the leaderboard of SemEval-2022 Task 8: Multilingual News Article Similarity. We propose an entity-enriched Siamese Transformer which computes news article similarity based on different sub-dimensions, such as the shared narrative, entities, location and time of the event discussed in the news article. Our system exploits a Siamese network architecture using a Transformer encoder to learn document-level representations for the purpose of capturing the narrative together with the auxiliary entity-based features extracted from the news articles. T…
We consider the problem of embedding character-entity relationships from the reduced semantic space of narratives, proposing and evaluating the assumption that these relationships hold under a reflection operation. We analyze this assumption and compare the approach to a baseline state-of-the-art model with a unique evaluation that simulates efficacy on a downstream clustering task with human-created labels. Although our model creates clusters that achieve Silhouette scores of -.084, outperforming the baseline -.227, our analysis reveals that the models approach the task much differently and p…
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Inc.（腾讯公司）
Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly \textbf{entity-wise}, which separately track each entity and independently predict different states of each entity. Such an entity-wise paradigm does not consider the interaction between entities and their states. In this paper, we propose a new \textbf{scene-wise} paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner. Based on this paradigm, we propose \textbf{S}…
UNC Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）；University of British Columbia（不列颠哥伦比亚大学）
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation. We study gender biases associated with the protagonist in model-generated stories. Such biases may be expressed either explicitly ("women can't park") or implicitly (e.g. an unsolicited male character guides her into a parking space). We focus on implicit biases, and use a commonsense reasoning engine to uncover them. Specifically, we infer and analyze the protagonist's motivations, attributes, mental states, and implications on others. Our findings regar…
Named entity recognition (NER) is an important task in narration extraction. Narration, as a system of stories, provides insights into how events and characters in the stories develop over time. This paper proposes an architecture for NER on a corpus about social purpose organizations. This is the first NER task specifically targeted at social service entities. We show how this approach can be used for the sequencing of services and impacted clients with information extracted from unstructured text. The methodology outlines steps for extracting ontological representation of entities such as ne…
Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
Fraunhofer Institute for Algorithms and Scientific Computing (SCAI)（弗劳恩霍夫算法与科学计算研究所（SCAI））；Kairntech SAS（Kairntech公司）；Bonn-Aachen International Center for Information Technology (b-it), University of Bonn（波恩大学波恩-亚琛国际信息技术中心（b-it））
Our lives are ruled by events of varying importance ranging from simple everyday occurrences to incidents of societal dimension. And a lot of effort is taken to exchange information and discuss about such events: generally speaking, stringent narratives are formed to reduce complexity. But when considering complex events like the current conflict between Russia and Ukraine it is easy to see that those events cannot be grasped by objective facts alone, like the start of the conflict or respective troop sizes. There are different viewpoints and assessments to consider, a different understanding …
EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs
The University of Manchester（曼彻斯特大学）；King’s College London（伦敦国王学院）；Huawei London Research Centre（华为伦敦研究中心）；Huawei Technologies Co., Ltd.（华为技术有限公司）；The Alan Turing Institute（艾伦·图灵研究所）
MBZUAI, UAE（阿联酋马斯喀特大学）；Nazarbayev University, Kazakhstan（哈萨克斯坦纳扎尔巴耶夫大学）；University of Maryland, USA（美国马里兰大学）；University of Arizona, USA（美国亚利桑那大学）；Athens University of Economics and Business, Greece（希腊雅典经济与商业大学）；University of Porto, Portugal（葡萄牙波尔图大学）；Sofia University "St. Kliment Ohridski", Bulgaria（保加利亚索菲亚大学）；University of Helsinki, Finland（芬兰赫尔辛基大学）；Beira Interior and INESC TEC, Portugal（葡萄牙贝拉内尔和INESC TEC）；Porto and INESC TEC, Portugal（葡萄牙波尔图和INESC TEC）；University of Padova, Italy（意大利帕多瓦大学）；European Commission Joint Research Center, Italy（意大利欧洲委员会联合研究中心）；Polish Academy of Sciences, Poland（波兰科学院）
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Information Sciences Institute & Computer Science, University of Southern California（南加州大学信息科学研究所与计算机科学系）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Understanding a narrative requires reading between the lines and reasoning about the unspoken but obvious implications about events and people's mental states - a capability that is trivial for humans but remarkably hard for machines. To facilitate research addressing this challenge, we introduce a new annotation framework to explain naive psychology of story characters as fully-specified chains of mental states with respect to motivations and emotional reactions. Our work presents a new large-scale dataset with rich low-level annotations and establishes baseline performance on several new tas…
Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives
School for Business and Society, University of York（约克大学商业与社会学院）；ESRC Vulnerability and Policing Futures Research Centre（经济与社会研究委员会脆弱性与警务未来研究中心）；School of Law, University of Leeds（利兹大学法学院）
Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries
Siebel School of Computing and Data Science, The Grainger College of Engineering, University of Illinois Urbana-Champaign（Siebel计算与数据科学学院，格拉inger工程学院，伊利诺伊大学厄巴纳-香槟分校）；Department of Psychology, College of Liberal Arts and Sciences, University of Illinois Urbana-Champaign（心理学系，文理学院，伊利诺伊大学厄巴纳-香槟分校）；School of Interactive Computing, College of Computing, Georgia Institute of Technology（交互计算学院，计算机学院，佐治亚理工学院）
Between Sense and Sensibility: Declarative narrativisation of mental models as a basis and benchmark for visuo-spatial cognition and computation focussed collaborative cognitive systems
University of Bremen（不来梅大学）
“\emph{sensing}”和“\emph{sensibility}”之间有什么区别？换句话说，什么样的认知过程介导了感知能力和可感知印象的形成-例如，抽象，类比，假设和理论的形成，信念和他们的修正，论点的形成-在特定领域的问题解决中，还是在日常生活，工作和简单地在环境中走动的常规活动中？如何才能知识和推理的能力，表现出人类在特定的问题背景下，被用来作为一个模型和基准的发展与人类的援助，保证和授权的协作认知（互动）系统？我们提出这些问题的背景下，一系列的辅助技术与\emph{visuo-spatial perception and cognition}任务，包括方面，如常识，创造力，专业领域的知识和解决问题的思维过程的应用。正在考虑的辅助技术包括：（a）人类活动解释;（b）高级认知旋转;（c）建筑和数字媒体创作等领域以人为本的创造性设计;（d）地理信息系统的定性分析。计算叙事不仅提供了丰富的认知基础，但他们也作为一个基准的功能性能在我们的发展计算认知辅助系统。我们认为，有关空间，行动和变化的计算叙事提供了一个有用的模型\emph{visual}和\emph{spatio-temporal thinking}在广泛的解决问题的任务和应用领域，协作认知系统可以提供一个辅助和授权功能。
Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）；Bosch Research（博世研究院）
Procedural text understanding is a challenging language reasoning task that requires models to track entity states across the development of a narrative. A complete procedural understanding solution should combine three core aspects: local and global views of the inputs, and global view of outputs. Prior methods considered a subset of these aspects, resulting in either low precision or low recall. In this paper, we propose Coalescing Global and Local Information (CGLI), a new model that builds entity- and timestep-aware input representations (local input) considering the whole context (global …
Across the financial domain, researchers answer complex questions by extensively "searching" for relevant information to generate long-form reports. This workshop paper discusses automating the construction of query-specific document and entity knowledge graphs (KGs) for complex research topics. We focus on the CODEC dataset, where domain experts (1) create challenging questions, (2) construct long natural language narratives, and (3) iteratively search and assess the relevance of documents and entities. For the construction of query-specific KGs, we show that state-of-the-art ranking systems …
Tsinghua University（清华大学）；Brigham and Women's Hospital（布莱根妇女医院）；VA Boston Healthcare System（VA波士顿医疗系统）；Harvard T.H. Chan School of Public Health（哈佛大学陈曾熙公共卫生学院）；Harvard Medical School（哈佛医学院）
Objective: Narrative text in Electronic health records (EHR) contain rich information for medical and data science studies. This paper introduces the design and performance of Narrative Information Linear Extraction (NILE), a natural language processing (NLP) package for EHR analysis that we share with the medical informatics community. Methods: NILE uses a modified prefix-tree search algorithm for named entity recognition, which can detect prefix and suffix sharing. The semantic analyses are implemented as rule-based finite state machines. Analyses include negation, location, modification, fa…
STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；UNSW Sydney（新南威尔士大学）；Chongqing University（重庆大学）
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
York University（约克大学）；Qatar Computing Research Institute (QCRI)（卡塔尔计算研究所）；Nanyang Technological University（南洋理工大学）；Dialpad Inc.（Dialpad公司）；Salesforce AI（Salesforce人工智能部门）
